INDEX

Explanations

phrases or words related to restrictions or prohibitions

oai_token-act-pair · gpt-3.5-turbo

negative phrases or terms, particularly focusing on the concept of "no" as a prefix to describe restrictions or limitations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥ¼ãĥĨ

-0.90

APTER

-0.81

å§«

-0.79

ãĥ¼ãĥĨãĤ£

-0.78

çīĪ

-0.77

 Reloaded

-0.76

Ń·

-0.75

gypt

-0.68

 Bohem

-0.68

 Royale

-0.67

POSITIVE LOGITS

brainer

1.04

reply

0.98

know

0.92

interest

0.92

matter

0.92

issue

0.91

notice

0.91

purpose

0.90

practice

0.90

move

0.89

Activations Density 0.018%

phrases or words related to restrictions or prohibitions

negative phrases or terms, particularly focusing on the concept of "no" as a prefix to describe restrictions or limitations

No Comments

No Known Activations